On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
This work quantifies the impact of training setup, synthesis choices, and attacker knowledge on privacy leakage and demonstrates that adversaries need not have perfect knowledge of the training setup, identical data distributions, or massive compute resources to construct successful attacks.
Behnoosh Zamanlooy, Elaheh Bassak, Fatemeh Tavakoli et al.
· 0 citations